Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. MLP Out - 65k
    5. 0-GEMMASCOPE-MLP-65K
    6. 61090
    Prev
    Next
    INDEX
    Explanations

    contrasting clauses or qualifying phrases within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oreilles
    -1.16
     élevées
    -1.11
     lèvres
    -1.00
     oídos
    -0.98
     prochaines
    -0.95
     européennes
    -0.95
     rêves
    -0.92
     côtés
    -0.92
     épaules
    -0.92
     vérit
    -0.91
    POSITIVE LOGITS
     faſt
    0.95
     viſ
    0.91
     raiſ
    0.88
     more
    0.87
     itſelf
    0.85
     unſ
    0.84
     cauſe
    0.84
     myſelf
    0.84
     ſever
    0.83
     tranſ
    0.83
    Activations Density 0.002%

    No Known Activations